Radar / AI models / Decision Models in Hugging Face

Decision Models in Hugging Face: a shared interface for models that decide instead of generating

Hugging Face added decision models to Transformers: models that take a state plus typed questions (Choice, Score, Noul) and return structured decisions with probabilities in a single forward pass, with DecisionPipeline, AutoModelForDecision, a /v1/systemone serving endpoint, llama.cpp GGUF support and a decision-model Hub tag.

new launchmodels · decisionJEV traction 0.51added 2026-11-11
Open Decision Models in Hugging Face →View on the radar

Why it matters

Asking an LLM to output JSON for every routing or triage call wastes tokens and latency: decision models make the decision itself a first-class output, and now Transformers, llama.cpp and the Hub all speak the same interface for them.

What you could build with it

A support team could replace a JSON-prompting LLM router with a decision model that returns a calibrated probability over billing, shipping, or technical categories in one forward pass, cutting latency and cost on every ticket triage.

Does it hold up?

Usable today for builders: DecisionPipeline and AutoModelForDecision ship in Transformers with a /v1/systemone endpoint and llama.cpp support; the post publishes no benchmarks, so the efficiency claim is still vendor-side.

Built with Decision Models in Hugging Face

Learn more

technical deep dive →

First spotted on article: source.

More AI models

VoiceStudio: open-source, fully-local ElevenLabs alternative for voice cloning, dubbing, and audiobooksdebpalash/VoiceStudio is a desktop app that runs voice cloning, voice design, video dubbing, dictation, transcription…models · JEV 0.75Edge0-145B: open 145B MoE that runs on a single consumer GPUEdge0 open-sourced 145B and 120B latent-MoE models derived from Qwen3.8-Flash-Next, plus an inference framework that…models · JEV 0.74Strata: run a 125B model on a gaming PCFree, MIT-licensed local inference engine that runs Qwen3.8-Flash-Next (125B MoE, about 6B active per token) on…models · JEV 0.73Google AI Edge Gallery: offline speech recognition and synthesis on-deviceGoogle added fully offline speech recognition and text-to-speech to AI Edge Gallery, with ML Kit APIs on Android and…models · JEV 0.73Soup: fine-tune an 8B LLM on a 4 GB laptop GPU from one YAML fileAn open-source CLI that fine-tunes LLMs from a single YAML file, with layer streaming that trains an 8B model on a 4…models · JEV 0.73Tencent Hunyuan Hy3: open 295B MoE with 21B active under Apache 2.0Tencent open-sourced Hy3, a 295B-parameter mixture-of-experts model with only 21B parameters active per token, under…models · JEV 0.73

Get the week's best AI launches, plus 3 ideas worth building

One email every Saturday. Ranked by traction, not hype. Free.